Stefan Horoi

Orcid: 0000-0003-2951-2600

According to our database1, Stefan Horoi authored at least 11 papers between 2020 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Less is More: Undertraining Experts Improves Model Upcycling.
CoRR, June, 2025

2024
Neural networks with optimized single-neuron adaptation uncover biologically plausible regularization.
PLoS Comput. Biol., 2024

Towards a General Recipe for Combinatorial Optimization With Multi-Filter GNNs.
Proceedings of the Learning on Graphs Conference, 26-29 November 2024, Virtual., 2024

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Non-Uniform Parameter-Wise Model Merging.
Proceedings of the IEEE International Conference on Big Data, 2024

2023
Reliability of CKA as a Similarity Measure in Deep Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
Exploring the Geometry and Topology of Neural Network Loss Landscapes.
Proceedings of the Advances in Intelligent Data Analysis XX, 2022

2021
Visualizing High-Dimensional Trajectories on the Loss-Landscape of ANNs.
CoRR, 2021

2020
Advantages of biologically-inspired adaptive neural activation in RNNs during learning.
CoRR, 2020

Internal representation dynamics and geometry in recurrent neural networks.
CoRR, 2020

Low-Dimensional Dynamics of Encoding and Learning in Recurrent Neural Networks.
Proceedings of the Advances in Artificial Intelligence, 2020


  Loading...